© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47970
    Prev
    Next
    INDEX
    Explanations

    apology for losses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     familiar
    -0.09
     suited
    -0.08
     detached
    -0.07
     PARTICULAR
    -0.07
     Axel
    -0.07
     RCS
    -0.07
     Rx
    -0.07
     Herr
    -0.07
     fragile
    -0.07
    chk
    -0.07
    POSITIVE LOGITS
     lost
    0.20
     losses
    0.19
     shortcomings
    0.19
     missed
    0.19
     earlier
    0.18
     deficiencies
    0.18
     loss
    0.17
     sins
    0.17
     inconvenience
    0.16
    lost
    0.16
    Activations Density 0.094%

    No Known Activations